Benchmark menu

Model results

GPT-OSS 120B

See how GPT-OSS 120B performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

GPT-OSS 120B

Provider: OpenAI

Rank
44
Status
Complete 3/3
Rank change
Baseline
Score
28.3
Last tested
2026-08-23
Settings tested
All settings tested

Scores by reasoning setting

Available settings

LowMediumHigh

Checked on 2026-07-30 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
Low14.5Tested and includedBaseline
Medium35.6Tested and includedBalanced
High34.8Tested and includedIntensive

How settings are grouped

  • Baseline: Low — tested and included
  • Balanced: Medium — tested and included
  • Intensive: High — tested and included

Player program results

High: 0% / 63% / 37% · n 8Medium: 13% / 75% / 12% · n 8Low: 63% / 25% / 12% · n 8 All settings testedMany programs needed repairMany programs failed

Generation cost

Average estimated cost
$0.0043
Median estimated cost
$0.0025
Estimated range
$0.000458–$0.02
Cost data
24 combinations / 24 recorded runs
Observed total
$0.10
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
13k tokens
Output range
1.3k–44k tokens
Samples
24

Estimated cost gives equal weight to each model, game, and reasoning-setting combination.

Test setup

  • Combines this model's tested reasoning settings
  • Uses the standard GameBench player-program prompt